arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.00977cs.LG
收藏

理解最优深度主动学习算法的行为

Towards Understanding the Behaviors of Optimal Deep Active Learning Algorithms

MIT CSAIL(麻省理工学院计算机科学与人工智能实验室);Facebook AI(脸书人工智能研究院)

Yilun Zhou, Adithya Renduchintala, Xian Li, Sida Wang, Yashar Mehdad, Asish Ghoshal

摘要:

主动学习(AL)算法可以用更少的数据实现更好的性能,因为模型指导数据选择过程。虽然已经提出了许多算法,但很少有关于最佳AL算法的研究,这将有助于研究人员了解他们的模型在设计上的不足和缺陷。在本文中,我们提出了一个模拟退火算法来搜索这个最佳的预言,并分析了几个任务。我们提出了定性和定量的见解,这个甲骨文的行为,比较和对比,他们与那些不同的甲骨文。此外,我们能够使用一个特定的洞察力来持续改进算法。我们希望我们的发现能更好地为未来的主动学习研究提供信息。该代码可在https://github.com/YilunZhou/optimal-active-learning上获得。

英文摘要:

Active learning (AL) algorithms may achieve better performance with fewer data because the model guides the data selection process. While many algorithms have been proposed, there is little study on what the optimal AL algorithm looks like, which would help researchers understand where their models fall short and iterate on the design. In this paper, we present a simulated annealing algorithm to search for this optimal oracle and analyze it for several tasks. We present qualitative and quantitative insights into the behaviors of this oracle, comparing and contrasting them with those of various heuristics. Moreover, we are able to consistently improve the heuristics using one particular insight. We hope that our findings can better inform future active learning research. The code is available at https://github.com/YilunZhou/optimal-active-learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑